Written by Jakub Rusinowski · Last updated August 15, 2026
Yes
Yes — Granite 4.0 Small-H 32B-A9B at Q8_0 needs about 36.6 GB of the 48 GB usable on Mac mini (M4 Pro, 64 GB) (~11.4 GB spare), at ~13.7 tok/s (estimated), with room for about 32,768 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~13.7 tok/s
| Usable memory for models | 48 GB |
| Memory bandwidth | 273 GB/s |
| Form factor | Mini PC |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 48 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 66.6 GB | ✗ No | — | — | 64 GB |
| Q8_0 | 36.6 GB | ✓ Yes | 32K | ~13.7 tok/s | 34 GB |
| Q6_K | 28.9 GB | ✓ Yes | 64K | ~17.1 tok/s | 26.2 GB |
| Q5_K_M | 25.3 GB | ✓ Yes | 64K | ~19.3 tok/s | 22.7 GB |
| Q4_K_M | 22 GB | ✓ Yes | 64K | ~22 tok/s | 19.3 GB |
| Q3_K_M | 16.3 GB | ✓ Yes | 128K | ~28.7 tok/s | 13.6 GB |
| Q2_K | 13.2 GB | ✓ Yes | 128K | ~34.6 tok/s | 10.5 GB |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes — Granite 4.0 Small-H 32B-A9B at Q8_0 needs about 36.6 GB of the 48 GB usable on Mac mini (M4 Pro, 64 GB) (~11.4 GB spare), at ~13.7 tok/s (estimated), with room for about 32,768 tokens of context.
Q8_0 — it needs about 36.6 GB of the 48 GB available, downloads as roughly 34 GB, and runs at an estimated 13.7 tokens/sec with up to 32K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
← Can I Run It? | IBM Granite 4.0 model page | Check your hardware